Multiple Sensor Gesture Recognition

1. A method for recognizing a multi-sensor gesture, comprising: receiving a plurality of sensor inputs; acquiring a first confidence threshold for determining that a first gesture has been performed based on a first sensor input of the plurality of sensor inputs; acquiring a second confidence threshold for determining that a second gesture has been performed based on a second sensor input of the plurality of sensor inputs; detecting a compensating event for the first sensor input; increasing the first confidence threshold in response to detecting the compensating event; detecting that the first gesture has been performed based on the increased first confidence threshold and the first sensor input; detecting that the second gesture has been performed based on the second confidence threshold and the second sensor input; determining that the multi-sensor gesture has been performed in response to detecting that both the first gesture and the second gesture have been performed; and executing a command on a computing system in response to determining that the multi-sensor gesture has been performed.

2. The method of claim 1 , further comprising: the first sensor input derives from a depth camera; the second sensor input derives from a microphone; and the determining that the multi-sensor gesture has been performed includes determining that a person has pointed to a particular virtual object using the first sensor input and that the person has said a particular word using the second sensor input.

3. The method of claim 1 , wherein: the first sensor input derives from a depth camera; and the detecting a compensating event includes detecting that an acceleration of the depth camera was above a particular threshold.

4. The method of claim 1 , wherein: the first sensor input derives from a depth sensor; and the detecting a compensating event includes detecting that a velocity of the depth sensor was above a particular threshold for more than a particular period of time.

5. The method of claim 1 , wherein: the first sensor input derives from an image sensor; and the detecting a compensating event includes detecting a lighting condition associated with the image sensor that was below a particular threshold for more than a particular period of time.

6. The method of claim 1 , wherein: the detecting a compensating event includes detecting that a temperature associated with the first sensor input was above a particular threshold for more than a particular period of time.

7. The method of claim 1 , further comprising: determining a time difference between the first sensor input and the second sensor input; and time shifting the first sensor input by the time difference.

8. The method of claim 1 , further comprising: receiving a request for an identification of the plurality of sensor inputs from a requesting application; identifying the plurality of sensor inputs in response to the receiving a request; and outputting the identification of the plurality of sensor inputs.

9. The method of claim 8 , wherein: the identification of the plurality of sensor inputs includes an identification of each sensor input of the plurality of sensor inputs.

10. The method of claim 1 , wherein: the increasing the first confidence threshold includes increasing the first confidence threshold from a first confidence value to a second confidence value greater than the first confidence value such that the minimum confidence value for detecting the first gesture using the first sensor input is increased.

11. An electronic device for recognizing a multi-sensor gesture, comprising: a first sensor, the first sensor generates a first sensor input; a second sensor, the second sensor generates a second sensor input; a memory, the memory stores a first confidence threshold for determining that a first gesture has been performed based on the first sensor input and a second confidence threshold for determining that a second gesture has been performed based on the second sensor input; and one or more processors, the one or more processors detect a compensating event for the first sensor input, the one or more processors increase the first confidence threshold in response to detecting the compensating event, the one or more processors detect that the first gesture has been performed based on the increased first confidence threshold and the first sensor input, the one or more processors detect that the second gesture has been performed based on the second confidence threshold and the second sensor input, the one or more processors determine that the multi-sensor gesture has been performed in response to detecting that both the first gesture and the second gesture have been performed.

12. The electronic device of claim 11 , wherein: the first sensor input derives from a depth camera; the second sensor input derives from a microphone; and the one or more processors determine that a person has pointed to a particular virtual object using the first sensor input and that the person has said a particular word using the second sensor input, the one or more processors determine that the multi-sensor gesture has been performed in response to determining that the person has pointed to the particular virtual object and that the person has said the particular word.

13. The electronic device of claim 11 , wherein: the first sensor includes a depth sensor; and the compensating event includes detecting that a velocity of the depth sensor was above a particular threshold for more than a particular period of time.

14. The electronic device of claim 11 , wherein: the compensating event includes detecting that a temperature of the first sensor was above a particular threshold for more than a particular period of time.

15. The electronic device of claim 11 , wherein: the one or more processors determine a time difference between the first sensor input and the second sensor input and synchronize the first sensor input and the second sensor input by time shifting the first sensor input by the time difference.

16. The electronic device of claim 11 , wherein: the first sensor includes a depth sensor; and the one or more processors detect the compensating event by detecting that an acceleration of the depth sensor was above a particular threshold.

17. One or more storage devices containing processor readable code for programming one or more processors to perform a method for operating a multi-sensor gesture recognition system comprising: receiving a plurality of sensor inputs, the plurality of sensor inputs includes a first sensor input and a second sensor input; synchronizing the first sensor input and the second sensor input, the synchronizing includes determining a time difference between the first sensor input and the second sensor input and time shifting the first sensor input by the time difference; acquiring a first confidence threshold for determining that a first gesture has been performed based on the first sensor input; acquiring a second confidence threshold for determining that a second gesture has been performed based on the second sensor input; detecting a compensating event for the first sensor input; increasing the first confidence threshold in response to detecting the compensating event; detecting that the first gesture has been performed based on the increased first confidence threshold and the first sensor input; detecting that the second gesture has been performed based on the second confidence threshold and the second sensor input; and determining that a multi-sensor gesture has been performed in response to detecting that both the first gesture and the second gesture have been performed.

18. The one or more storage devices of claim 17 , wherein: the first sensor input is derived from a depth sensor; and the detecting a compensating event includes detecting that a velocity of the depth sensor was above a particular threshold for more than a particular period of time.

19. The one or more storage devices of claim 18 , further comprising: detecting that a new sensor input is available for recognizing the multi-sensor gesture; adding the new sensor input to the plurality of sensor inputs; and adjusting the second confidence threshold in response to adding the new sensor input to the plurality of sensor inputs.

20. The one or more storage devices of claim 17 , wherein: the first sensor input is derived from an image sensor; and the detecting a compensating event includes detecting that a lighting condition associated with the image sensor was below a particular threshold for more than a particular period of time.